© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 6741
    Prev
    Next
    INDEX
    Explanations

    information or Google search

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     প্রতি
    0.40
    ributedString
    0.40
    textAppearance
    0.40
    ⁡</
    0.39
     образовањем
    0.39
    slideDuplicate
    0.39
    ('*
    0.38
     ermöglicht
    0.38
    ▿
    0.38
     обстанов
    0.38
    POSITIVE LOGITS
     $+\
    0.45
     $\
    0.43
     certain
    0.42
     unique
    0.42
     play
    0.40
     ave
    0.40
    Play
    0.39
     $=\
    0.39
     body
    0.39
     hold
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.